jules

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the @google/jules CLI globally via NPM. This package is provided by a well-known technology provider.
  • [COMMAND_EXECUTION]: Uses git, gh, and jules shell commands to automate repository context extraction and task management.
  • [PROMPT_INJECTION]: The skill ingests pull request data via the GitHub CLI which presents a surface for indirect prompt injection. 1. Ingestion points: Pull request title, body, and file paths are retrieved via gh pr view. 2. Boundary markers: No explicit delimiters or isolation instructions are used. 3. Capability inventory: The skill utilizes subprocess calls to git and jules to modify the repository. 4. Sanitization: No validation or filtering is applied to the ingested metadata before it is passed to the AI agent. This behavior is consistent with the primary purpose of a code-review and task-delegation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:53 PM
Security Audit — agent-trust-hub — jules